Exploring the dependence of gas cooling and heating functions on the incident radiation field with machine learning

Journal Article · 18 December 2023 · Monthly Notices of the Royal Astronomical Society

DOI: https://doi.org/10.1093/mnras/stad3880 · OSTI ID:2281436

Robinson, David  ^[1]; Avestruz, Camille  ^[1]; Gnedin, Nickolay Y. ^[2]

---

1. Univ. of Michigan, Ann Arbor, MI (United States)
2. Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Univ. of Chicago, IL (United States). Kavli Inst. for Cosmological Physics (KICP)

Gas cooling and heating functions play a crucial role in galaxy formation. But, it is computationally expensive to exactly compute these functions in the presence of an incident radiation field. These computations can be greatly sped up by using interpolation tables of pre-computed values, at the expense of making significant and sometimes even unjustified approximations. Here, we explore the capacity of machine learning to approximate cooling and heating functions with a generalized radiation field. Specifically, we use the machine learning algorithm XGBOOST to predict cooling and heating functions calculated with the photoionization code cloudy at fixed metallicity, using different combinations of photoionization rates as features. We perform a constrained quadratic fit in metallicity to enable a fair comparison with traditional interpolation methods at arbitrary metallicity. We consider the relative importance of various photoionization rates through both a principal component analysis (PCA) and calculation of SHapley Additive exPlanation (SHAP) values for our XGBOOST models. We use feature importance information to select different subsets of rates to use in model training. Our XGBOOST models outperform a traditional interpolation approach at each fixed metallicity, regardless of feature selection. At arbitrary metallicity, we are able to reduce the frequency of the largest cooling and heating function errors compared to an interpolation table. We find that the primary bottleneck to increasing accuracy lies in accurately capturing the metallicity dependence. This study demonstrates the potential of machine learning methods such as XGBOOST to capture the non-linear behaviour of cooling and heating functions.

• Research Organization: Univ. of Michigan, Ann Arbor, MI (United States); Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Oak Ridge Institute for Science and Education (ORISE), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Office of Workforce Development for Teachers & Scientists (WDTS); USDOE Office of Science (SC), High Energy Physics (HEP); USDOE
• Grant/Contract Number: SC0019193; AC02-07CH11359; SC0014664; SC009193
• OSTI ID: 2281436
• Alternate ID(s): OSTI ID: 2283708; OSTI ID: 2350809
• Report Number(s): FERMILAB-PUB-23-347-T; arXiv:2310.09328; TRN: US2411223
• Journal Information: Monthly Notices of the Royal Astronomical Society, Vol. 528, Issue 1; ISSN 0035-8711
• Publisher: Oxford University PressCopyright Statement
• Country of Publication: United States
• Language: English